Chinese character recognition software OCR application

The task of the Chinese character recognition software is to study how to make the computer “literate”. This system usually uses a photoelectric conversion device to convert the Chinese character or word box into an electric signal and send it to a computer. The computer automatically recognizes and reads it, so it is called optics. Character Recognition (OCR).

OCR Development Profile

The concept of OCR was first proposed by German scientist Tausheck in 1929. Later American scientist Handel also proposed the idea of ​​using technology to identify words. The earliest research on printed Chinese character recognition was Casey and Nagy of IBM. In 1966, they published the first article on Chinese character recognition and used the template matching method to identify 1000 printed Chinese characters. In the early 1970s, Japanese scholars began to study Chinese character recognition and did a lot of work. The study of Chinese character recognition started relatively late in China, and research work on OCR began in the late 1970s. Early OCR software failed to meet actual requirements due to various factors such as recognition rate and productization. At the same time, due to the high cost of hardware equipment and slow operation, it has not reached a practical level. Only some departments, such as the information department, press and publishing unit, use OCR software. After 1986, China's OCR research has made great progress. There have been innovations in Chinese character modeling and recognition methods. Great achievements have been made in system development and application, and many companies have successively launched Chinese OCR products. After entering the 1990s, with the wide application of flatbed scanners and the popularization of information automation and office automation in China, OCR technology has greatly promoted the further development, so that the accuracy of OCR recognition, recognition speed to meet the majority of users Claim.

At present, there are many popular OCR softwares. The OCR in English mainly includes OmniPage, and the Chinese OCR are mainly Tsinghua Unisplendour OCR, Tsinghua Wentong OCR, Hanwang OCR, Zhongjing Shangshu OCR, Danqing OCR, and Mengzi OCR. Although Chinese characters are large in size and complex in shape, OCR technology has matured. Many OCR software can not only recognize black-and-white printed Chinese characters, but also recognize gray and color printed Chinese characters. The recognition speed is fast, and the recognition accuracy rate is over 99%. It can recognize various fonts and fonts such as Song, Black, and Carcass. Traditional; can recognize multiple fonts, different sizes of shuffle; some OCR software can also identify images, tables. At the same time, great progress has been made in the study of handwritten Chinese character recognition, and the correct recognition rate has reached more than 70%.

Application of OCR Software

In the scanner market, many types of office and home scanners are equipped with OCR software, such as the violet scanner is equipped with a violet OCR, the Microtek scanner is equipped with a book OCR, the Mustek scanner is equipped with Danqing OCR and so on. Scanners and OCR software share the entire process from document input to text recognition.

Document scanning is often used in the office area. Scanning documents are scanned for related documents published in newspapers, magazines, and other media. Then they are OCR-recognized or stored as image files, which can be later recognized by OCR and converted into text. File or Word file is stored.

In addition, the storage and transmission of digital information is not only low-cost, high-efficiency, but also able to adapt to the constant development needs of typesetting, network transmission and so on. At present, there are a large number of books, newspapers, magazines, and other paper treasures left over from history, and it is urgently needed to convert them into electronic information. Such as the establishment of the e-library, it is necessary to scan the books page by page, and the recognition of the OCR software has replaced the work of manually typing texts, greatly shortening the entry time, reducing labor intensity, saving manpower and reducing costs. Improve the accuracy of entry, work efficiency and modern office automation.

At present, the collocation of OCR software and scanners has been applied to many fields in the information age, such as digital libraries, identification of various reports, and identification of bank and tax system documents. With the development and popularization of networking and informatization, its application scope will become more and more extensive.

The composition of OCR system

The function of Chinese character recognition software OCR is to identify all kinds of figures or images of Chinese characters in printed characters or handwritings by computer, and to mark out Chinese character category codes. Therefore, Chinese character recognition is ultimately an image recognition problem. Due to the large volume of Chinese characters, their different fonts and fonts, and their complex structure, the process of Chinese character recognition is extremely complicated. OCR software workflow diagram, as follows:

Document Data → Scan Input → Image Processing → Layout Division → Text Recognition → Text Editing → Document Storage

Due to the popularity and wide application of scanners, OCR software only needs to provide an interface with the scanner and use the scanner driver software. Therefore, OCR software is mainly composed of four parts: an image processing module, a layout division module, a character recognition module, and a text editing module. (to be continued)